Web Search on GAIA (Pass@1)
87.4Pass@1Seed1.8
Evaluation Results
| Method | Links | |
|---|---|---|
| Seed1.82026.03 | 87.4 | |
| GPT-5 High2026.03 | 76.7 | |
| Gemini 3-pro2026.03 | 74.8 | |
| Claude-4-Sonnet2025.12 | 68.3 | |
| Claude Sonnet-4.52026.03 | 66 | |
| Gemini 2.5-pro2026.03 | 57.3 | |
| ASearcher-Web-QwQparameters=32B2025.12 | 52.8 | |
| MiroThinker-8B-DPO-v0.1parameters=8B2025.12 | 46.6 | |
| FoldAct-7Bp_drop=0, parameters=7B2025.12 | 46.3 | |
| FoldAct-7Bp_drop=0.5, parameters=7B2025.12 | 45 | |
| WebSailor-7Bparameters=7B2025.12 | 33 | |
| GPT-4.1-mini2025.12 | 32.73 |